Live data from Hacker News

Viewing profile — sophiabits

sophiabits

HN member
Joined
Mon, Feb 13, 2023, 9:30 AM UTC
HN karma
259
Public activity
71 items

About sophiabits

sophiabits.com/blog

Recent public activity

  1. comment
    Comment #48491688

    > You can't fire Claude if it fucks up What's the difference between "firing" Claude vs moving to a model from a different provider? The latter seems very analogous to firing an em…

  2. comment
    Comment #48378347

    TIL you can get RSS feeds for YouTube channels. Thanks for this!

  3. comment
    Comment #48143121

    > Selfishly, I don't want my screen scraped because it feels like an invasion of my privacy, [...] But zooming out, I don't want to live in a world where humans—employees or otherw…

  4. comment
    Comment #48103305

    I do not envy the position the npm team are in. They removed the ability to unpublish packages as a response to the left-pad incident[1] because it wasn't desirable for individual …

  5. comment
    Comment #48001905

    A browser is OOM more expensive to run than a terminal app, regardless of what you're running inside said browser

  6. comment
    Comment #47781429

    Purchasing power is probably a better metric in a vacuum, but it's hard to analyze accurately For example, the comment you're citing is claiming that because minimum wage has incre…

  7. comment
    Comment #47209810

    > the MCP server is automatically launched when the Agent loads that skill The main problem with this approach at the moment is it busts your prompt cache, because LLMs expect all …

  8. comment
    Comment #45422373

    Comments are often the best tool for explaining why a bit of code is formulated how it is, or explaining why a more obvious alternate implementation is a dead end. An example of th…

  9. story
  10. story
  11. comment
    Comment #41176133

    I’ve especially noticed this with gpt-4o-mini [1], and it’s a big problem. My particular use case involves keeping a running summary of a conversation between a user and the LLM, a…

  12. comment
    Comment #41165379

    I wanted to document a particular genAI antipattern which I've seen a few times now. LLMs are theoretically pretty fungible, because you send English and get English back--but in p…

  13. story
  14. comment
    Comment #40638131

    Even with this setup in place you need a heightened level of caution relative to a monolith. In a monolith I can refactor function signatures however I desire because the whole ser…

  15. comment
    Comment #40622076

    Not sure what the situation is like now, but we stopped using LangChain last year because the rate of change in the library was huge. Whenever we needed to upgrade for a new featur…

  16. comment
    Comment #40622053

    The other possibility (which is common in startups) is that often the “right way” is different depending on the scale of the system you need to design for. In cases like this you e…

  17. comment
    Comment #40622014

    Big fan of this. Here in New Zealand we have a slogan “be a tidy kiwi” that encourages people to pick up their litter and be good stewards of for our natural environment Imo the sa…

  18. comment
    Comment #40186685

    This already exists (in a slightly different prompt format); it's the underlying idea behind ReAct: https://react-lm.github.io As you say, I'm skeptical this counts as AGI. Althoug…

  19. comment
    Comment #40155327

    This sounds like an argument against TypeScript in general, no? e.g. If I am parsing a string to a number via Number.parseInt, I don’t need a “: number” annotation because I can ju…

  20. comment
    Comment #40155261

    Happens a lot with junction tables ime. e.g. At my last job we had three tables: user, stream, user_stream. user_stream is an N:N junction between a user and a stream A user is fre…

  21. comment
    Comment #39197613

    Type-prefixed IDs are the way to go. For completeness it's worth noting that the first example using the `string | 'currentNode'` type can be slightly improved in cases where you _…

  22. comment
    Comment #39197432

    There’s a French think tank called “The Shift Project” which actually produced a report estimating CO2 impact of data transfer a few years ago [1]! The numbers are obviously very r…

  23. comment
    Comment #38876413

    The problem is that you don’t really know if your mock accurately implements the behavior of the database. The only way you could verify the mock behaves correctly would be to run …

  24. comment
    Comment #38789163

    Yeah, the folks working on aider (AI pair programming) [1] found that these kind of tricks reduced performance for them. I’m pretty confident there will be situations where you can…

  25. comment
    Comment #38761229

    Yeah +1 We originally started out building features with LangChain (loading chains from YAML sounded good—it felt like it would be easy to get non-engineers to help with prompt dev…